A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges

arXiv:2405.00476v1 Announce Type: new
Abstract: Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to capture structural, temporal, and contextual relationships in dynamic graphs simultaneously, leading to enhanced performance in various applications. As the demand for dynamic GNNs continues to grow, numerous models and frameworks have emerged to cater to different application needs. There is a pressing need for a comprehensive survey that evaluates the performance, strengths, and limitations of various approaches in this domain. This paper aims to …

abstract applications arxiv benchmarks challenges cs.lg demand dynamic frameworks gnns graph graph neural networks graphs information networks neural networks performance relationships survey temporal type